Which distributional cues help the most? Unsupervised contexts selection for lexical category acquisition

TitleWhich distributional cues help the most? Unsupervised contexts selection for lexical category acquisition
Publication TypeConference Proceedings
Year of Publication2015
AuthorsCassani, G., Grimm R., Daelemans W., & Gillis S.
Conference NameSixth Workshop on Cognitive Aspects of Computational Language Learning (CogACLL 2015), Lisbon, Portugal
Conference LocationLisbon
Keywordscomputational psycholinguistics, Distributional bootstrapping, frame-based approaches, language acquisition, Lexical categories induction
Abstract

Starting from the distributional bootstrapping hypothesis, we propose an unsupervised model that selects the most useful distributional information according to its salience in the input, incorporating psycholinguistic evidence. With a supervised Parts-of-Speech tagging experiment, we provide preliminary results suggesting that the distributional contexts extracted by our model yield similar performances as compared to current approaches from the literature, with a gain in psychological plausibility. We also introduce a more principled way to evaluate the effectiveness of distributional contexts in helping learners to group words in syntactic categories.

AttachmentSize
distributional-cues-unsupervised.pdf175.26 KB
PDF